Triple
T26235157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lord Howe Island stick insect |
E656145
|
entity |
| Predicate | maleSizeRelativeToFemale |
P41339
|
FINISHED |
| Object | smaller |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: smaller | Statement: [Lord Howe Island stick insect, maleSizeRelativeToFemale, smaller]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maleSizeRelativeToFemale Context triple: [Lord Howe Island stick insect, maleSizeRelativeToFemale, smaller]
-
A.
maleSmallerThanFemale
chosen
Indicates that, within a male–female pair, the male individual is smaller in size than the female individual.
-
B.
hasGenderRatioMale
Indicates the proportion or percentage of male individuals within a given population or group.
-
C.
genderRatio
Indicates the proportional relationship between different genders within a given group or population.
-
D.
hasGenderRatioFemale
Indicates the proportion or percentage of females relative to the total population in the described group or context.
-
E.
maleLargerThan
Indicates that the male individual in a pair is larger in size than the corresponding female or other compared individual.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ee5b4b8b408190993da38c0067cc8d |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69f60d897ae081909d9cac57cbda3e00 |
completed | May 2, 2026, 2:43 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fd90fc81909055b211368f9139 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 9:01 p.m.